A Claude Code plugin that adds skills for language-server diagnostics, rename safety checks, project rule handling, and removing AI-generated code smells from a single file, plus comment-checker feedback and a goal-driven work loop.
Claude Code
> /plugin marketplace add code-yeongyu/lazyclaudecode> /plugin install omo@sisyphuslabs
Codex
$ npx skills add code-yeongyu/lazyclaudecode -a codex
Cursor
$ npx skills add code-yeongyu/lazyclaudecode -a cursor
Gemini CLI
$ npx skills add code-yeongyu/lazyclaudecode -a gemini-cli
GitHub Copilot
$ copilot plugin marketplace add code-yeongyu/lazyclaudecode$ copilot plugin install omo@sisyphuslabs
OpenCode
$ npx skills add code-yeongyu/lazyclaudecode -a opencode
Windsurf
$ npx skills add code-yeongyu/lazyclaudecode -a windsurf
The lazy way to run omo inside Claude Code. A native Claude Code plugin marketplace by Sisyphus Labs.
What it is · Install · Components · MCP · Telemetry · omo
omo for Claude Code brings the omo experience — rule injection, comment checking, LSP intelligence, ultrawork orchestration, durable ultragoal tracking, and start-work continuation — into Claude Code through Claude Code's native plugin system.
This repository is the distribution surface: a native Claude Code plugin
marketplace. The marketplace is named sisyphuslabs and ships a single
plugin named omo. The repository name (lazyclaudecode) is the install
alias and the home of this marketplace — it is not the marketplace name.
The marketplace name is
sisyphuslabs. The plugin name isomo. You install the plugin asomo@sisyphuslabs.
Everything is self-contained: hooks, skills, subagents, and the bundled MCP
servers all resolve from ${CLAUDE_PLUGIN_ROOT}, so the plugin runs correctly
straight from the Claude Code plugin cache.
Add this marketplace, then install the omo plugin:
/plugin marketplace add code-yeongyu/lazyclaudecode
/plugin install omo@sisyphuslabs
# Claude Code platform (cc is the short alias for claudecode):
bunx omo install --platform=cc
# or via the dedicated alias (same compiled CLI, defaults to Claude Code):
bunx lazyclaudecode install
The omo CLI shells out to claude plugin marketplace add code-yeongyu/lazyclaudecode
and claude plugin install omo@sisyphuslabs. If claude is not on your PATH,
it prints the two /plugin commands above so you can run them inside a Claude
Code session.
omo is one plugin namespace; each capability stays isolated internally as a
component.
| Component | What it does |
|---|---|
| rules | Injects AGENTS.md / CLAUDE.md / .omo/rules/** into context via SessionStart, UserPromptSubmit, PostToolUse, and PostCompact. |
| comment-checker | Runs comment-checker after Write / Edit / MultiEdit tool use to keep comments honest. |
| lsp | Exposes Language Server Protocol diagnostics, navigation, symbols, and rename through MCP plus post-edit hooks. |
| ultrawork | Detects ultrawork / ulw in a prompt and injects the full ultrawork orchestration directive. |
| ultragoal | Durable, repo-native multi-goal orchestration with embedded success criteria and an observable evidence audit under .omo/ultragoal/, scoped per Claude Code session. |
| start-work-continuation | A Stop / SubagentStop continuation hook that resumes .omo/boulder.json start-work plans, keyed per Claude Code session. |
| telemetry | Anonymous, opt-out daily-active signal emitted on the plugin SessionStart hook. |
omo bundles two MCP servers, wired through ${CLAUDE_PLUGIN_ROOT} so they
spawn cleanly from the plugin cache:
| Server | Purpose |
|---|---|
| ast_grep | Structural code search and rewrite via ast-grep. |
| lsp | Language Server Protocol tools: diagnostics, definitions, references, symbols, rename. |
Installing omo registers a library of skills (init-deep, planning,
refactor, remove-ai-slops, review-work, start-work, and more) and a set of
subagents for orchestrated work:
| Subagent | Role | Model |
|---|---|---|
| reviewer | Reviews ultrawork output against the directive. | opus |
| metis | Strategic planning and decomposition. | opus |
| planner | Turns objectives into executable plans. | opus |
| momus | Adversarial critique of plans and changes. | opus |
| explorer | Fast, read-only codebase reconnaissance. | haiku |
| librarian | Fast, read-only documentation and reference lookup. | haiku |
Skills carry a Claude Code Harness Tool Compatibility section so they speak in
Claude Code's native verbs (Edit, Write, MultiEdit, Task).
omo for Claude Code sends an anonymous, at-most-once-per-UTC-day "still alive"
signal so the project can gauge real-world usage. It uses the same PostHog
project as the wider omo family but emits the distinct event
omo_claude_daily_active. The signal is keyed to a SHA256-hashed installation
identifier, person profiles are suppressed, and the daily dedup state is stored
locally.
# Claude Code only:
export OMO_CLAUDE_DISABLE_POSTHOG=1
export OMO_CLAUDE_SEND_ANONYMOUS_TELEMETRY=0
# Globally (also silences the rest of the omo family):
export OMO_DISABLE_POSTHOG=1
export OMO_SEND_ANONYMOUS_TELEMETRY=0
Setting OMO_DISABLE_POSTHOG disables omo for Claude Code telemetry too — the
global flag is inherited.
omo ships in editions tuned to each agent harness. They all share the same
core ideas and the same sisyphuslabs identity.
| Edition | Harness | Distribution |
|---|---|---|
| Ultimate | OpenCode | omo OpenCode plugin |
| Light (Codex) | OpenAI Codex | lazycodex |
| Light (Claude Code) | Claude Code | this repo — lazyclaudecode |
All editions descend from oh-my-openagent (omo).
MIT © Yeongyu Kim
Stars on GitHub
View @code-yeongyu’s profileA Codex plugin with skills, agents, and MCP servers for development work. Includes diagnostics, LSP code intelligence, comment checking, and tools for reporting and fixing bugs in LazyCodex and Codex CLI.
@code-yeongyuA Codex and Claude Code plugin for agent orchestration, with skills for LSP diagnostics, comment-checker feedback, health checks, and filing bug reports for LazyCodex and omo-codex.
@code-yeongyuKeeps long multi-step coding work on track inside Codex. It holds project context across sessions, plans the work, carries it out one step at a time, and checks the result before calling the task done.
@code-yeongyuA development methodology for coding agents that makes the agent brainstorm before building, follow plans, run parallel work and finish branches in a disciplined way. You get fewer skipped steps and more consistent results from your coding assistant.
@obraHelps you take a change from a rough idea or bug report through to a tested, reviewed result, with each step handled by a focused skill. Its skills cover pinning down domain terms, designing module interfaces, diagnosing hard bugs, and reviewing changes against your repo's coding standards.
@mattpocockGives your coding agent a planning, testing and review routine to follow on every task. It plans before building, checks changes with tests, has a fresh reviewer look for regressions, and saves repeated wins as reusable skills.
@affaan-mDeveloper tools for working on the React codebase itself. Provides skills for extracting error messages, managing and debugging feature flags across release channels, running Flow type checks, and fixing lint and formatting issues before committing.
@facebookA Claude Code plugin that adds skills for language-server diagnostics, rename safety checks, project rule handling, and removing AI-generated code smells from a single file, plus comment-checker feedback and a goal-driven work loop. Install it with the command on its page. It includes comment-checker, lsp, rules. Its skills do not fire on their own yet. Free and open source.
Is this plugin yours?
Claim it with GitHubSubmit a pluginPromote it